X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/a34b95aa7ba5fd4838541d1cdcd28358fb808062..59caaf5ca771cd80c74253fd26b2671eb199b8bf:/librarian/__init__.py?ds=sidebyside diff --git a/librarian/__init__.py b/librarian/__init__.py index dd09ce4..b257b79 100644 --- a/librarian/__init__.py +++ b/librarian/__init__.py @@ -8,24 +8,34 @@ from __future__ import with_statement import os import re import shutil +import urllib -class ParseError(Exception): + +class UnicodeException(Exception): def __str__(self): """ Dirty workaround for Python Unicode handling problems. """ - return self.message + return unicode(self).encode('utf-8') def __unicode__(self): """ Dirty workaround for Python Unicode handling problems. """ - return self.message + args = self.args[0] if len(self.args) == 1 else self.args + try: + message = unicode(args) + except UnicodeDecodeError: + message = unicode(args, encoding='utf-8', errors='ignore') + return message + +class ParseError(UnicodeException): + pass -class ValidationError(Exception): +class ValidationError(UnicodeException): pass class NoDublinCore(ValidationError): """There's no DublinCore section, and it's required.""" pass -class NoProvider(Exception): +class NoProvider(UnicodeException): """There's no DocProvider specified, and it's needed.""" pass @@ -55,12 +65,14 @@ class EmptyNamespace(XMLNamespace): return tag # some common namespaces we use +XMLNS = XMLNamespace('http://www.w3.org/XML/1998/namespace') RDFNS = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#') DCNS = XMLNamespace('http://purl.org/dc/elements/1.1/') XINS = XMLNamespace("http://www.w3.org/2001/XInclude") XHTMLNS = XMLNamespace("http://www.w3.org/1999/xhtml") NCXNS = XMLNamespace("http://www.daisy.org/z3986/2005/ncx/") OPFNS = XMLNamespace("http://www.idpf.org/2007/opf") +PLMETNS = XMLNamespace("http://dl.psnc.pl/schemas/plmet/") WLNS = EmptyNamespace() @@ -70,7 +82,7 @@ class WLURI(object): slug = None example = 'http://wolnelektury.pl/katalog/lektura/template/' - _re_wl_uri = re.compile('http://wolnelektury.pl/katalog/lektura/' + _re_wl_uri = re.compile(r'http://(www\.)?wolnelektury.pl/katalog/lektura/' '(?P[-a-z0-9]+)/?$') def __init__(self, uri): @@ -82,8 +94,8 @@ class WLURI(object): def strict(cls, uri): match = cls._re_wl_uri.match(uri) if not match: - raise ValueError('Supplied URI (%s) does not match ' - 'the template: %s.' % (uri, cls._re_wl_uri)) + raise ValidationError(u'Invalid URI (%s). Should match: %s' % ( + uri, cls._re_wl_uri.pattern)) return cls(uri) @classmethod @@ -264,3 +276,8 @@ class OutputFile(object): if not os.path.isdir(dirname): os.makedirs(dirname) shutil.copy(self.get_filename(), path) + + +class URLOpener(urllib.FancyURLopener): + version = 'FNP Librarian (http://github.com/fnp/librarian)' +urllib._urlopener = URLOpener()